1 files changed, 561 insertions, 304 deletions

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 42de98d73ff..d76f0b70c6e 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -20,6 +20,8 @@
  * 02110-1301 USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -32,129 +34,209 @@
 #include <linux/list.h>
 #include <linux/platform_device.h>
 #include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
-#include <asm/smp.h>
+#include <asm/cpu_device_id.h>
 
 #define DRVNAME	"coretemp"
 
-typedef enum { SHOW_TEMP, SHOW_TJMAX, SHOW_TTARGET, SHOW_LABEL,
-		SHOW_NAME } SHOW;
-
 /*
- * Functions declaration
+ * force_tjmax only matters when TjMax can't be read from the CPU itself.
+ * When set, it replaces the driver's suboptimal heuristic.
  */
+static int force_tjmax;
+module_param_named(tjmax, force_tjmax, int, 0444);
+MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
-static struct coretemp_data *coretemp_update_device(struct device *dev);
+#define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
+#define NUM_REAL_CORES		32	/* Number of Real cores per cpu */
+#define CORETEMP_NAME_LENGTH	19	/* String Length of attrs */
+#define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
+#define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
+#define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
 
-struct coretemp_data {
-	struct device *hwmon_dev;
-	struct mutex update_lock;
-	const char *name;
-	u32 id;
-	u16 core_id;
-	char valid;		/* zero until following fields are valid */
-	unsigned long last_updated;	/* in jiffies */
+#define TO_PHYS_ID(cpu)		(cpu_data(cpu).phys_proc_id)
+#define TO_CORE_ID(cpu)		(cpu_data(cpu).cpu_core_id)
+#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
+
+#ifdef CONFIG_SMP
+#define for_each_sibling(i, cpu)	for_each_cpu(i, cpu_sibling_mask(cpu))
+#else
+#define for_each_sibling(i, cpu)	for (i = 0; false; )
+#endif
+
+/*
+ * Per-Core Temperature Data
+ * @last_updated: The time when the current temperature value was updated
+ *		earlier (in jiffies).
+ * @cpu_core_id: The CPU Core from which temperature values should be read
+ *		This value is passed as "id" field to rdmsr/wrmsr functions.
+ * @status_reg: One of IA32_THERM_STATUS or IA32_PACKAGE_THERM_STATUS,
+ *		from where the temperature values should be read.
+ * @attr_size:  Total number of pre-core attrs displayed in the sysfs.
+ * @is_pkg_data: If this is 1, the temp_data holds pkgtemp data.
+ *		Otherwise, temp_data holds coretemp data.
+ * @valid: If this is 1, the current temperature is valid.
+ */
+struct temp_data {
 	int temp;
-	int tjmax;
 	int ttarget;
-	u8 alarm;
+	int tjmax;
+	unsigned long last_updated;
+	unsigned int cpu;
+	u32 cpu_core_id;
+	u32 status_reg;
+	int attr_size;
+	bool is_pkg_data;
+	bool valid;
+	struct sensor_device_attribute sd_attrs[TOTAL_ATTRS];
+	char attr_name[TOTAL_ATTRS][CORETEMP_NAME_LENGTH];
+	struct attribute *attrs[TOTAL_ATTRS + 1];
+	struct attribute_group attr_group;
+	struct mutex update_lock;
 };
 
-/*
- * Sysfs stuff
- */
+/* Platform Data per Physical CPU */
+struct platform_data {
+	struct device *hwmon_dev;
+	u16 phys_proc_id;
+	struct temp_data *core_data[MAX_CORE_DATA];
+	struct device_attribute name_attr;
+};
+
+struct pdev_entry {
+	struct list_head list;
+	struct platform_device *pdev;
+	u16 phys_proc_id;
+};
+
+static LIST_HEAD(pdev_list);
+static DEFINE_MUTEX(pdev_list_mutex);
 
-static ssize_t show_name(struct device *dev, struct device_attribute
-			  *devattr, char *buf)
+static ssize_t show_label(struct device *dev,
+				struct device_attribute *devattr, char *buf)
 {
-	int ret;
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct coretemp_data *data = dev_get_drvdata(dev);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
 
-	if (attr->index == SHOW_NAME)
-		ret = sprintf(buf, "%s\n", data->name);
-	else	/* show label */
-		ret = sprintf(buf, "Core %d\n", data->core_id);
-	return ret;
+	if (tdata->is_pkg_data)
+		return sprintf(buf, "Physical id %u\n", pdata->phys_proc_id);
+
+	return sprintf(buf, "Core %u\n", tdata->cpu_core_id);
 }
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute
-			  *devattr, char *buf)
+static ssize_t show_crit_alarm(struct device *dev,
+				struct device_attribute *devattr, char *buf)
 {
-	struct coretemp_data *data = coretemp_update_device(dev);
-	/* read the Out-of-spec log, never clear */
-	return sprintf(buf, "%d\n", data->alarm);
+	u32 eax, edx;
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
+
+	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
+
+	return sprintf(buf, "%d\n", (eax >> 5) & 1);
 }
 
-static ssize_t show_temp(struct device *dev,
-			 struct device_attribute *devattr, char *buf)
+static ssize_t show_tjmax(struct device *dev,
+			struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct coretemp_data *data = coretemp_update_device(dev);
-	int err;
+	struct platform_data *pdata = dev_get_drvdata(dev);
 
-	if (attr->index == SHOW_TEMP)
-		err = data->valid ? sprintf(buf, "%d\n", data->temp) : -EAGAIN;
-	else if (attr->index == SHOW_TJMAX)
-		err = sprintf(buf, "%d\n", data->tjmax);
-	else
-		err = sprintf(buf, "%d\n", data->ttarget);
-	return err;
+	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
 }
 
-static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL,
-			  SHOW_TEMP);
-static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp, NULL,
-			  SHOW_TJMAX);
-static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, show_temp, NULL,
-			  SHOW_TTARGET);
-static DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL);
-static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_name, NULL, SHOW_LABEL);
-static SENSOR_DEVICE_ATTR(name, S_IRUGO, show_name, NULL, SHOW_NAME);
-
-static struct attribute *coretemp_attributes[] = {
-	&sensor_dev_attr_name.dev_attr.attr,
-	&sensor_dev_attr_temp1_label.dev_attr.attr,
-	&dev_attr_temp1_crit_alarm.attr,
-	&sensor_dev_attr_temp1_input.dev_attr.attr,
-	&sensor_dev_attr_temp1_crit.dev_attr.attr,
-	NULL
-};
+static ssize_t show_ttarget(struct device *dev,
+				struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
 
-static const struct attribute_group coretemp_group = {
-	.attrs = coretemp_attributes,
-};
+	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
+}
 
-static struct coretemp_data *coretemp_update_device(struct device *dev)
+static ssize_t show_temp(struct device *dev,
+			struct device_attribute *devattr, char *buf)
 {
-	struct coretemp_data *data = dev_get_drvdata(dev);
-
-	mutex_lock(&data->update_lock);
+	u32 eax, edx;
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
 
-	if (!data->valid || time_after(jiffies, data->last_updated + HZ)) {
-		u32 eax, edx;
+	mutex_lock(&tdata->update_lock);
 
-		data->valid = 0;
-		rdmsr_on_cpu(data->id, MSR_IA32_THERM_STATUS, &eax, &edx);
-		data->alarm = (eax >> 5) & 1;
-		/* update only if data has been valid */
-		if (eax & 0x80000000) {
-			data->temp = data->tjmax - (((eax >> 16)
-							& 0x7f) * 1000);
-			data->valid = 1;
-		} else {
-			dev_dbg(dev, "Temperature data invalid (0x%x)\n", eax);
-		}
-		data->last_updated = jiffies;
+	/* Check whether the time interval has elapsed */
+	if (!tdata->valid || time_after(jiffies, tdata->last_updated + HZ)) {
+		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
+		/*
+		 * Ignore the valid bit. In all observed cases the register
+		 * value is either low or zero if the valid bit is 0.
+		 * Return it instead of reporting an error which doesn't
+		 * really help at all.
+		 */
+		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
+		tdata->valid = 1;
+		tdata->last_updated = jiffies;
 	}
 
-	mutex_unlock(&data->update_lock);
-	return data;
+	mutex_unlock(&tdata->update_lock);
+	return sprintf(buf, "%d\n", tdata->temp);
 }
 
-static int __devinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
+struct tjmax_pci {
+	unsigned int device;
+	int tjmax;
+};
+
+static const struct tjmax_pci tjmax_pci_table[] = {
+	{ 0x0708, 110000 },	/* CE41x0 (Sodaville ) */
+	{ 0x0c72, 102000 },	/* Atom S1240 (Centerton) */
+	{ 0x0c73, 95000 },	/* Atom S1220 (Centerton) */
+	{ 0x0c75, 95000 },	/* Atom S1260 (Centerton) */
+};
+
+struct tjmax {
+	char const *id;
+	int tjmax;
+};
+
+static const struct tjmax tjmax_table[] = {
+	{ "CPU  230", 100000 },		/* Model 0x1c, stepping 2	*/
+	{ "CPU  330", 125000 },		/* Model 0x1c, stepping 2	*/
+};
+
+struct tjmax_model {
+	u8 model;
+	u8 mask;
+	int tjmax;
+};
+
+#define ANY 0xff
+
+static const struct tjmax_model tjmax_model_table[] = {
+	{ 0x1c, 10, 100000 },	/* D4xx, K4xx, N4xx, D5xx, K5xx, N5xx */
+	{ 0x1c, ANY, 90000 },	/* Z5xx, N2xx, possibly others
+				 * Note: Also matches 230 and 330,
+				 * which are covered by tjmax_table
+				 */
+	{ 0x26, ANY, 90000 },	/* Atom Tunnel Creek (Exx), Lincroft (Z6xx)
+				 * Note: TjMax for E6xxT is 110C, but CPU type
+				 * is undetectable by software
+				 */
+	{ 0x27, ANY, 90000 },	/* Atom Medfield (Z2460) */
+	{ 0x35, ANY, 90000 },	/* Atom Clover Trail/Cloverview (Z27x0) */
+	{ 0x36, ANY, 100000 },	/* Atom Cedar Trail/Cedarview (N2xxx, D2xxx)
+				 * Also matches S12x0 (stepping 9), covered by
+				 * PCI table
+				 */
+};
+
+static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 {
 	/* The 100C is default for both mobile and non mobile CPUs */
 
@@ -163,39 +245,46 @@ static int __devinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *
 	int usemsr_ee = 1;
 	int err;
 	u32 eax, edx;
-	struct pci_dev *host_bridge;
-
-	/* Early chips have no MSR for TjMax */
+	int i;
+	struct pci_dev *host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
 
-	if ((c->x86_model == 0xf) && (c->x86_mask < 4)) {
-		usemsr_ee = 0;
+	/*
+	 * Explicit tjmax table entries override heuristics.
+	 * First try PCI host bridge IDs, followed by model ID strings
+	 * and model/stepping information.
+	 */
+	if (host_bridge && host_bridge->vendor == PCI_VENDOR_ID_INTEL) {
+		for (i = 0; i < ARRAY_SIZE(tjmax_pci_table); i++) {
+			if (host_bridge->device == tjmax_pci_table[i].device)
+				return tjmax_pci_table[i].tjmax;
+		}
 	}
 
-	/* Atom CPUs */
-
-	if (c->x86_model == 0x1c) {
-		usemsr_ee = 0;
+	for (i = 0; i < ARRAY_SIZE(tjmax_table); i++) {
+		if (strstr(c->x86_model_id, tjmax_table[i].id))
+			return tjmax_table[i].tjmax;
+	}
 
-		host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
+	for (i = 0; i < ARRAY_SIZE(tjmax_model_table); i++) {
+		const struct tjmax_model *tm = &tjmax_model_table[i];
+		if (c->x86_model == tm->model &&
+		    (tm->mask == ANY || c->x86_mask == tm->mask))
+			return tm->tjmax;
+	}
 
-		if (host_bridge && host_bridge->vendor == PCI_VENDOR_ID_INTEL
-		    && (host_bridge->device == 0xa000	/* NM10 based nettop */
-		    || host_bridge->device == 0xa010))	/* NM10 based netbook */
-			tjmax = 100000;
-		else
-			tjmax = 90000;
+	/* Early chips have no MSR for TjMax */
 
-		pci_dev_put(host_bridge);
-	}
+	if (c->x86_model == 0xf && c->x86_mask < 4)
+		usemsr_ee = 0;
 
-	if ((c->x86_model > 0xe) && (usemsr_ee)) {
+	if (c->x86_model > 0xe && usemsr_ee) {
 		u8 platform_id;
 
-		/* Now we can detect the mobile CPU using Intel provided table
-		   http://softwarecommunity.intel.com/Wiki/Mobility/720.htm
-		   For Core2 cores, check MSR 0x17, bit 28 1 = Mobile CPU
-		*/
-
+		/*
+		 * Now we can detect the mobile CPU using Intel provided table
+		 * http://softwarecommunity.intel.com/Wiki/Mobility/720.htm
+		 * For Core2 cores, check MSR 0x17, bit 28 1 = Mobile CPU
+		 */
 		err = rdmsr_safe_on_cpu(id, 0x17, &eax, &edx);
 		if (err) {
 			dev_warn(dev,
@@ -203,20 +292,26 @@ static int __devinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *
 				 " CPU\n");
 			usemsr_ee = 0;
 		} else if (c->x86_model < 0x17 && !(eax & 0x10000000)) {
-			/* Trust bit 28 up to Penryn, I could not find any
-			   documentation on that; if you happen to know
-			   someone at Intel please ask */
+			/*
+			 * Trust bit 28 up to Penryn, I could not find any
+			 * documentation on that; if you happen to know
+			 * someone at Intel please ask
+			 */
 			usemsr_ee = 0;
 		} else {
 			/* Platform ID bits 52:50 (EDX starts at bit 32) */
 			platform_id = (edx >> 18) & 0x7;
 
-			/* Mobile Penryn CPU seems to be platform ID 7 or 5
-			  (guesswork) */
-			if ((c->x86_model == 0x17) &&
-			    ((platform_id == 5) || (platform_id == 7))) {
-				/* If MSR EE bit is set, set it to 90 degrees C,
-				   otherwise 105 degrees C */
+			/*
+			 * Mobile Penryn CPU seems to be platform ID 7 or 5
+			 * (guesswork)
+			 */
+			if (c->x86_model == 0x17 &&
+			    (platform_id == 5 || platform_id == 7)) {
+				/*
+				 * If MSR EE bit is set, set it to 90 degrees C,
+				 * otherwise 105 degrees C
+				 */
 				tjmax_ee = 90000;
 				tjmax = 105000;
 			}
@@ -224,7 +319,6 @@ static int __devinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *
 	}
 
 	if (usemsr_ee) {
-
 		err = rdmsr_safe_on_cpu(id, 0xee, &eax, &edx);
 		if (err) {
 			dev_warn(dev,
@@ -233,180 +327,270 @@ static int __devinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *
 		} else if (eax & 0x40000000) {
 			tjmax = tjmax_ee;
 		}
-	/* if we dont use msr EE it means we are desktop CPU (with exeception
-	   of Atom) */
 	} else if (tjmax == 100000) {
+		/*
+		 * If we don't use msr EE it means we are desktop CPU
+		 * (with exeception of Atom)
+		 */
 		dev_warn(dev, "Using relative temperature scale!\n");
 	}
 
 	return tjmax;
 }
 
-static int __devinit get_tjmax(struct cpuinfo_x86 *c, u32 id,
-			       struct device *dev)
+static bool cpu_has_tjmax(struct cpuinfo_x86 *c)
+{
+	u8 model = c->x86_model;
+
+	return model > 0xe &&
+	       model != 0x1c &&
+	       model != 0x26 &&
+	       model != 0x27 &&
+	       model != 0x35 &&
+	       model != 0x36;
+}
+
+static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 {
-	/* The 100C is default for both mobile and non mobile CPUs */
 	int err;
 	u32 eax, edx;
 	u32 val;
 
-	/* A new feature of current Intel(R) processors, the
-	   IA32_TEMPERATURE_TARGET contains the TjMax value */
+	/*
+	 * A new feature of current Intel(R) processors, the
+	 * IA32_TEMPERATURE_TARGET contains the TjMax value
+	 */
 	err = rdmsr_safe_on_cpu(id, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
 	if (err) {
-		dev_warn(dev, "Unable to read TjMax from CPU.\n");
+		if (cpu_has_tjmax(c))
+			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
 	} else {
 		val = (eax >> 16) & 0xff;
 		/*
 		 * If the TjMax is not plausible, an assumption
 		 * will be used
 		 */
-		if ((val > 80) && (val < 120)) {
-			dev_info(dev, "TjMax is %d C.\n", val);
+		if (val) {
+			dev_dbg(dev, "TjMax is %d degrees C\n", val);
 			return val * 1000;
 		}
 	}
 
+	if (force_tjmax) {
+		dev_notice(dev, "TjMax forced to %d degrees C by user\n",
+			   force_tjmax);
+		return force_tjmax * 1000;
+	}
+
 	/*
 	 * An assumption is made for early CPUs and unreadable MSR.
-	 * NOTE: the given value may not be correct.
+	 * NOTE: the calculated value may not be correct.
 	 */
+	return adjust_tjmax(c, id, dev);
+}
 
-	switch (c->x86_model) {
-	case 0xe:
-	case 0xf:
-	case 0x16:
-	case 0x1a:
-		dev_warn(dev, "TjMax is assumed as 100 C!\n");
-		return 100000;
-	case 0x17:
-	case 0x1c:		/* Atom CPUs */
-		return adjust_tjmax(c, id, dev);
-	default:
-		dev_warn(dev, "CPU (model=0x%x) is not supported yet,"
-			" using default TjMax of 100C.\n", c->x86_model);
-		return 100000;
+static int create_core_attrs(struct temp_data *tdata, struct device *dev,
+			     int attr_no)
+{
+	int i;
+	static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
+			struct device_attribute *devattr, char *buf) = {
+			show_label, show_crit_alarm, show_temp, show_tjmax,
+			show_ttarget };
+	static const char *const names[TOTAL_ATTRS] = {
+					"temp%d_label", "temp%d_crit_alarm",
+					"temp%d_input", "temp%d_crit",
+					"temp%d_max" };
+
+	for (i = 0; i < tdata->attr_size; i++) {
+		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, names[i],
+			attr_no);
+		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
+		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
+		tdata->sd_attrs[i].dev_attr.attr.mode = S_IRUGO;
+		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
+		tdata->sd_attrs[i].index = attr_no;
+		tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr;
 	}
+	tdata->attr_group.attrs = tdata->attrs;
+	return sysfs_create_group(&dev->kobj, &tdata->attr_group);
 }
 
-static void __devinit get_ucode_rev_on_cpu(void *edx)
+
+static int chk_ucode_version(unsigned int cpu)
 {
-	u32 eax;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
-	sync_core();
-	rdmsr(MSR_IA32_UCODE_REV, eax, *(u32 *)edx);
+	/*
+	 * Check if we have problem with errata AE18 of Core processors:
+	 * Readings might stop update when processor visited too deep sleep,
+	 * fixed for stepping D0 (6EC).
+	 */
+	if (c->x86_model == 0xe && c->x86_mask < 0xc && c->microcode < 0x39) {
+		pr_err("Errata AE18 not fixed, update BIOS or microcode of the CPU!\n");
+		return -ENODEV;
+	}
+	return 0;
 }
 
-static int __devinit coretemp_probe(struct platform_device *pdev)
+static struct platform_device *coretemp_get_pdev(unsigned int cpu)
 {
-	struct coretemp_data *data;
-	struct cpuinfo_x86 *c = &cpu_data(pdev->id);
-	int err;
-	u32 eax, edx;
+	u16 phys_proc_id = TO_PHYS_ID(cpu);
+	struct pdev_entry *p;
 
-	if (!(data = kzalloc(sizeof(struct coretemp_data), GFP_KERNEL))) {
-		err = -ENOMEM;
-		dev_err(&pdev->dev, "Out of memory\n");
-		goto exit;
-	}
+	mutex_lock(&pdev_list_mutex);
 
-	data->id = pdev->id;
-#ifdef CONFIG_SMP
-	data->core_id = c->cpu_core_id;
-#endif
-	data->name = "coretemp";
-	mutex_init(&data->update_lock);
+	list_for_each_entry(p, &pdev_list, list)
+		if (p->phys_proc_id == phys_proc_id) {
+			mutex_unlock(&pdev_list_mutex);
+			return p->pdev;
+		}
 
-	/* test if we can access the THERM_STATUS MSR */
-	err = rdmsr_safe_on_cpu(data->id, MSR_IA32_THERM_STATUS, &eax, &edx);
-	if (err) {
-		dev_err(&pdev->dev,
-			"Unable to access THERM_STATUS MSR, giving up\n");
-		goto exit_free;
-	}
+	mutex_unlock(&pdev_list_mutex);
+	return NULL;
+}
 
-	/* Check if we have problem with errata AE18 of Core processors:
-	   Readings might stop update when processor visited too deep sleep,
-	   fixed for stepping D0 (6EC).
-	*/
+static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
+{
+	struct temp_data *tdata;
+
+	tdata = kzalloc(sizeof(struct temp_data), GFP_KERNEL);
+	if (!tdata)
+		return NULL;
+
+	tdata->status_reg = pkg_flag ? MSR_IA32_PACKAGE_THERM_STATUS :
+							MSR_IA32_THERM_STATUS;
+	tdata->is_pkg_data = pkg_flag;
+	tdata->cpu = cpu;
+	tdata->cpu_core_id = TO_CORE_ID(cpu);
+	tdata->attr_size = MAX_CORE_ATTRS;
+	mutex_init(&tdata->update_lock);
+	return tdata;
+}
 
-	if ((c->x86_model == 0xe) && (c->x86_mask < 0xc)) {
-		/* check for microcode update */
-		err = smp_call_function_single(data->id, get_ucode_rev_on_cpu,
-					       &edx, 1);
-		if (err) {
-			dev_err(&pdev->dev,
-				"Cannot determine microcode revision of "
-				"CPU#%u (%d)!\n", data->id, err);
-			err = -ENODEV;
-			goto exit_free;
-		} else if (edx < 0x39) {
-			err = -ENODEV;
-			dev_err(&pdev->dev,
-				"Errata AE18 not fixed, update BIOS or "
-				"microcode of the CPU!\n");
-			goto exit_free;
-		}
-	}
+static int create_core_data(struct platform_device *pdev, unsigned int cpu,
+			    int pkg_flag)
+{
+	struct temp_data *tdata;
+	struct platform_data *pdata = platform_get_drvdata(pdev);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	u32 eax, edx;
+	int err, attr_no;
+
+	/*
+	 * Find attr number for sysfs:
+	 * We map the attr number to core id of the CPU
+	 * The attr number is always core id + 2
+	 * The Pkgtemp will always show up as temp1_*, if available
+	 */
+	attr_no = pkg_flag ? 1 : TO_ATTR_NO(cpu);
 
-	data->tjmax = get_tjmax(c, data->id, &pdev->dev);
-	platform_set_drvdata(pdev, data);
+	if (attr_no > MAX_CORE_DATA - 1)
+		return -ERANGE;
 
 	/*
-	 * read the still undocumented IA32_TEMPERATURE_TARGET. It exists
-	 * on older CPUs but not in this register,
-	 * Atoms don't have it either.
+	 * Provide a single set of attributes for all HT siblings of a core
+	 * to avoid duplicate sensors (the processor ID and core ID of all
+	 * HT siblings of a core are the same).
+	 * Skip if a HT sibling of this core is already registered.
+	 * This is not an error.
 	 */
+	if (pdata->core_data[attr_no] != NULL)
+		return 0;
 
-	if ((c->x86_model > 0xe) && (c->x86_model != 0x1c)) {
-		err = rdmsr_safe_on_cpu(data->id, MSR_IA32_TEMPERATURE_TARGET,
-		    &eax, &edx);
-		if (err) {
-			dev_warn(&pdev->dev, "Unable to read"
-					" IA32_TEMPERATURE_TARGET MSR\n");
-		} else {
-			data->ttarget = data->tjmax -
-					(((eax >> 8) & 0xff) * 1000);
-			err = device_create_file(&pdev->dev,
-					&sensor_dev_attr_temp1_max.dev_attr);
-			if (err)
-				goto exit_free;
+	tdata = init_temp_data(cpu, pkg_flag);
+	if (!tdata)
+		return -ENOMEM;
+
+	/* Test if we can access the status register */
+	err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx);
+	if (err)
+		goto exit_free;
+
+	/* We can access status register. Get Critical Temperature */
+	tdata->tjmax = get_tjmax(c, cpu, &pdev->dev);
+
+	/*
+	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
+	 * The target temperature is available on older CPUs but not in this
+	 * register. Atoms don't have the register at all.
+	 */
+	if (c->x86_model > 0xe && c->x86_model != 0x1c) {
+		err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET,
+					&eax, &edx);
+		if (!err) {
+			tdata->ttarget
+			  = tdata->tjmax - ((eax >> 8) & 0xff) * 1000;
+			tdata->attr_size++;
 		}
 	}
 
-	if ((err = sysfs_create_group(&pdev->dev.kobj, &coretemp_group)))
-		goto exit_dev;
+	pdata->core_data[attr_no] = tdata;
 
-	data->hwmon_dev = hwmon_device_register(&pdev->dev);
-	if (IS_ERR(data->hwmon_dev)) {
-		err = PTR_ERR(data->hwmon_dev);
-		dev_err(&pdev->dev, "Class registration failed (%d)\n",
-			err);
-		goto exit_class;
-	}
+	/* Create sysfs interfaces */
+	err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no);
+	if (err)
+		goto exit_free;
 
 	return 0;
-
-exit_class:
-	sysfs_remove_group(&pdev->dev.kobj, &coretemp_group);
-exit_dev:
-	device_remove_file(&pdev->dev, &sensor_dev_attr_temp1_max.dev_attr);
 exit_free:
-	kfree(data);
-exit:
+	pdata->core_data[attr_no] = NULL;
+	kfree(tdata);
 	return err;
 }
 
-static int __devexit coretemp_remove(struct platform_device *pdev)
+static void coretemp_add_core(unsigned int cpu, int pkg_flag)
+{
+	struct platform_device *pdev = coretemp_get_pdev(cpu);
+	int err;
+
+	if (!pdev)
+		return;
+
+	err = create_core_data(pdev, cpu, pkg_flag);
+	if (err)
+		dev_err(&pdev->dev, "Adding Core %u failed\n", cpu);
+}
+
+static void coretemp_remove_core(struct platform_data *pdata,
+				 int indx)
+{
+	struct temp_data *tdata = pdata->core_data[indx];
+
+	/* Remove the sysfs attributes */
+	sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group);
+
+	kfree(pdata->core_data[indx]);
+	pdata->core_data[indx] = NULL;
+}
+
+static int coretemp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct platform_data *pdata;
+
+	/* Initialize the per-package data structures */
+	pdata = devm_kzalloc(dev, sizeof(struct platform_data), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	pdata->phys_proc_id = pdev->id;
+	platform_set_drvdata(pdev, pdata);
+
+	pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME,
+								  pdata, NULL);
+	return PTR_ERR_OR_ZERO(pdata->hwmon_dev);
+}
+
+static int coretemp_remove(struct platform_device *pdev)
 {
-	struct coretemp_data *data = platform_get_drvdata(pdev);
+	struct platform_data *pdata = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = MAX_CORE_DATA - 1; i >= 0; --i)
+		if (pdata->core_data[i])
+			coretemp_remove_core(pdata, i);
 
-	hwmon_device_unregister(data->hwmon_dev);
-	sysfs_remove_group(&pdev->dev.kobj, &coretemp_group);
-	device_remove_file(&pdev->dev, &sensor_dev_attr_temp1_max.dev_attr);
-	platform_set_drvdata(pdev, NULL);
-	kfree(data);
 	return 0;
 }
 
@@ -416,57 +600,21 @@ static struct platform_driver coretemp_driver = {
 		.name = DRVNAME,
 	},
 	.probe = coretemp_probe,
-	.remove = __devexit_p(coretemp_remove),
-};
-
-struct pdev_entry {
-	struct list_head list;
-	struct platform_device *pdev;
-	unsigned int cpu;
-#ifdef CONFIG_SMP
-	u16 phys_proc_id;
-	u16 cpu_core_id;
-#endif
+	.remove = coretemp_remove,
 };
 
-static LIST_HEAD(pdev_list);
-static DEFINE_MUTEX(pdev_list_mutex);
-
-static int __cpuinit coretemp_device_add(unsigned int cpu)
+static int coretemp_device_add(unsigned int cpu)
 {
 	int err;
 	struct platform_device *pdev;
 	struct pdev_entry *pdev_entry;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-
-	/*
-	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
-	 * sensors. We check this bit only, all the early CPUs
-	 * without thermal sensors will be filtered out.
-	 */
-	if (!cpu_has(c, X86_FEATURE_DTS)) {
-		printk(KERN_INFO DRVNAME ": CPU (model=0x%x)"
-		       " has no thermal sensor.\n", c->x86_model);
-		return 0;
-	}
 
 	mutex_lock(&pdev_list_mutex);
 
-#ifdef CONFIG_SMP
-	/* Skip second HT entry of each core */
-	list_for_each_entry(pdev_entry, &pdev_list, list) {
-		if (c->phys_proc_id == pdev_entry->phys_proc_id &&
-		    c->cpu_core_id == pdev_entry->cpu_core_id) {
-			err = 0;	/* Not an error */
-			goto exit;
-		}
-	}
-#endif
-
-	pdev = platform_device_alloc(DRVNAME, cpu);
+	pdev = platform_device_alloc(DRVNAME, TO_PHYS_ID(cpu));
 	if (!pdev) {
 		err = -ENOMEM;
-		printk(KERN_ERR DRVNAME ": Device allocation failed\n");
+		pr_err("Device allocation failed\n");
 		goto exit;
 	}
 
@@ -478,17 +626,13 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)
 
 	err = platform_device_add(pdev);
 	if (err) {
-		printk(KERN_ERR DRVNAME ": Device addition failed (%d)\n",
-		       err);
+		pr_err("Device addition failed (%d)\n", err);
 		goto exit_device_free;
 	}
 
 	pdev_entry->pdev = pdev;
-	pdev_entry->cpu = cpu;
-#ifdef CONFIG_SMP
-	pdev_entry->phys_proc_id = c->phys_proc_id;
-	pdev_entry->cpu_core_id = c->cpu_core_id;
-#endif
+	pdev_entry->phys_proc_id = pdev->id;
+
 	list_add_tail(&pdev_entry->list, &pdev_list);
 	mutex_unlock(&pdev_list_mutex);
 
@@ -503,29 +647,127 @@ exit:
 	return err;
 }
 
-static void __cpuinit coretemp_device_remove(unsigned int cpu)
+static void coretemp_device_remove(unsigned int cpu)
 {
-	struct pdev_entry *p;
-	unsigned int i;
+	struct pdev_entry *p, *n;
+	u16 phys_proc_id = TO_PHYS_ID(cpu);
 
 	mutex_lock(&pdev_list_mutex);
-	list_for_each_entry(p, &pdev_list, list) {
-		if (p->cpu != cpu)
+	list_for_each_entry_safe(p, n, &pdev_list, list) {
+		if (p->phys_proc_id != phys_proc_id)
 			continue;
-
 		platform_device_unregister(p->pdev);
 		list_del(&p->list);
-		mutex_unlock(&pdev_list_mutex);
 		kfree(p);
-		for_each_cpu(i, cpu_sibling_mask(cpu))
-			if (i != cpu && !coretemp_device_add(i))
-				break;
-		return;
 	}
 	mutex_unlock(&pdev_list_mutex);
 }
 
-static int __cpuinit coretemp_cpu_callback(struct notifier_block *nfb,
+static bool is_any_core_online(struct platform_data *pdata)
+{
+	int i;
+
+	/* Find online cores, except pkgtemp data */
+	for (i = MAX_CORE_DATA - 1; i >= 0; --i) {
+		if (pdata->core_data[i] &&
+			!pdata->core_data[i]->is_pkg_data) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static void get_core_online(unsigned int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct platform_device *pdev = coretemp_get_pdev(cpu);
+	int err;
+
+	/*
+	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
+	 * sensors. We check this bit only, all the early CPUs
+	 * without thermal sensors will be filtered out.
+	 */
+	if (!cpu_has(c, X86_FEATURE_DTHERM))
+		return;
+
+	if (!pdev) {
+		/* Check the microcode version of the CPU */
+		if (chk_ucode_version(cpu))
+			return;
+
+		/*
+		 * Alright, we have DTS support.
+		 * We are bringing the _first_ core in this pkg
+		 * online. So, initialize per-pkg data structures and
+		 * then bring this core online.
+		 */
+		err = coretemp_device_add(cpu);
+		if (err)
+			return;
+		/*
+		 * Check whether pkgtemp support is available.
+		 * If so, add interfaces for pkgtemp.
+		 */
+		if (cpu_has(c, X86_FEATURE_PTS))
+			coretemp_add_core(cpu, 1);
+	}
+	/*
+	 * Physical CPU device already exists.
+	 * So, just add interfaces for this core.
+	 */
+	coretemp_add_core(cpu, 0);
+}
+
+static void put_core_offline(unsigned int cpu)
+{
+	int i, indx;
+	struct platform_data *pdata;
+	struct platform_device *pdev = coretemp_get_pdev(cpu);
+
+	/* If the physical CPU device does not exist, just return */
+	if (!pdev)
+		return;
+
+	pdata = platform_get_drvdata(pdev);
+
+	indx = TO_ATTR_NO(cpu);
+
+	/* The core id is too big, just return */
+	if (indx > MAX_CORE_DATA - 1)
+		return;
+
+	if (pdata->core_data[indx] && pdata->core_data[indx]->cpu == cpu)
+		coretemp_remove_core(pdata, indx);
+
+	/*
+	 * If a HT sibling of a core is taken offline, but another HT sibling
+	 * of the same core is still online, register the alternate sibling.
+	 * This ensures that exactly one set of attributes is provided as long
+	 * as at least one HT sibling of a core is online.
+	 */
+	for_each_sibling(i, cpu) {
+		if (i != cpu) {
+			get_core_online(i);
+			/*
+			 * Display temperature sensor data for one HT sibling
+			 * per core only, so abort the loop after one such
+			 * sibling has been found.
+			 */
+			break;
+		}
+	}
+	/*
+	 * If all cores in this pkg are offline, remove the device.
+	 * coretemp_device_remove calls unregister_platform_device,
+	 * which in turn calls coretemp_remove. This removes the
+	 * pkgtemp entry and does other clean ups.
+	 */
+	if (!is_any_core_online(pdata))
+		coretemp_device_remove(cpu);
+}
+
+static int coretemp_cpu_callback(struct notifier_block *nfb,
 				 unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long) hcpu;
@@ -533,10 +775,10 @@ static int __cpuinit coretemp_cpu_callback(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
-		coretemp_device_add(cpu);
+		get_core_online(cpu);
 		break;
 	case CPU_DOWN_PREPARE:
-		coretemp_device_remove(cpu);
+		put_core_offline(cpu);
 		break;
 	}
 	return NOTIFY_OK;
@@ -546,29 +788,42 @@ static struct notifier_block coretemp_cpu_notifier __refdata = {
 	.notifier_call = coretemp_cpu_callback,
 };
 
+static const struct x86_cpu_id __initconst coretemp_ids[] = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTHERM },
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, coretemp_ids);
+
 static int __init coretemp_init(void)
 {
-	int i, err = -ENODEV;
+	int i, err;
 
-	/* quick check if we run Intel */
-	if (cpu_data(0).x86_vendor != X86_VENDOR_INTEL)
-		goto exit;
+	/*
+	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
+	 * sensors. We check this bit only, all the early CPUs
+	 * without thermal sensors will be filtered out.
+	 */
+	if (!x86_match_cpu(coretemp_ids))
+		return -ENODEV;
 
 	err = platform_driver_register(&coretemp_driver);
 	if (err)
 		goto exit;
 
+	cpu_notifier_register_begin();
 	for_each_online_cpu(i)
-		coretemp_device_add(i);
+		get_core_online(i);
 
 #ifndef CONFIG_HOTPLUG_CPU
 	if (list_empty(&pdev_list)) {
+		cpu_notifier_register_done();
 		err = -ENODEV;
 		goto exit_driver_unreg;
 	}
 #endif
 
-	register_hotcpu_notifier(&coretemp_cpu_notifier);
+	__register_hotcpu_notifier(&coretemp_cpu_notifier);
+	cpu_notifier_register_done();
 	return 0;
 
 #ifndef CONFIG_HOTPLUG_CPU
@@ -583,7 +838,8 @@ static void __exit coretemp_exit(void)
 {
 	struct pdev_entry *p, *n;
 
-	unregister_hotcpu_notifier(&coretemp_cpu_notifier);
+	cpu_notifier_register_begin();
+	__unregister_hotcpu_notifier(&coretemp_cpu_notifier);
 	mutex_lock(&pdev_list_mutex);
 	list_for_each_entry_safe(p, n, &pdev_list, list) {
 		platform_device_unregister(p->pdev);
@@ -591,6 +847,7 @@ static void __exit coretemp_exit(void)
 		kfree(p);
 	}
 	mutex_unlock(&pdev_list_mutex);
+	cpu_notifier_register_done();
 	platform_driver_unregister(&coretemp_driver);
 }